Skip to main content
Use vercelAI() when your app calls generateText, streamText, or an AI SDK agent. The integration supports AI SDK v7 and v6. It creates one Lemma trace for each AI SDK run, extracts the prompt or messages as trace input, and records model calls and tool executions as child spans.

​
Install

npm install @uselemma/tracing ai zod

​
AI SDK v7

Create the Lemma telemetry integration once, then pass it to the AI SDK telemetry.integrations option. Use telemetry.functionId for the agent name. 
import { generateText, tool } from "ai";
import { z } from "zod";
import { vercelAI } from "@uselemma/tracing";

const lemmaTelemetry = vercelAI({
  apiKey: process.env.LEMMA_API_KEY,
  projectId: process.env.LEMMA_PROJECT_ID,
});

const result = await generateText({
  model,
  prompt: userMessage,
  tools: {
    searchDocs: tool({
      inputSchema: z.object({
        query: z.string(),
      }),
      execute: async ({ query }) => searchDocs(query),
    }),
  },
  telemetry: {
    functionId: "support-agent",
    metadata: {
      threadId: conversationId,
      userId: user.id,
    },
    integrations: [lemmaTelemetry],
  },
});

return result.text;

​
AI SDK v6

For AI SDK v6, pass the same helper through experimental_telemetry.integrations. Use experimental_telemetry.functionId for the agent name. 
import { generateText, tool } from "ai";
import { z } from "zod";
import { vercelAI } from "@uselemma/tracing";

const lemmaTelemetry = vercelAI({
  apiKey: process.env.LEMMA_API_KEY,
  projectId: process.env.LEMMA_PROJECT_ID,
});

const result = await generateText({
  model,
  prompt: userMessage,
  tools: {
    searchDocs: tool({
      inputSchema: z.object({
        query: z.string(),
      }),
      execute: async ({ query }) => searchDocs(query),
    }),
  },
  experimental_telemetry: {
    functionId: "support-agent",
    metadata: {
      threadId: conversationId,
      userId: user.id,
    },
    integrations: [lemmaTelemetry],
  },
});

return result.text;

​
Streaming

Use the same integration with streamText. 
import { streamText } from "ai";
import { vercelAI } from "@uselemma/tracing";

const lemmaTelemetry = vercelAI({
  apiKey: process.env.LEMMA_API_KEY,
  projectId: process.env.LEMMA_PROJECT_ID,
});

const result = streamText({
  model,
  prompt: userMessage,
  telemetry: {
    functionId: "support-agent",
    integrations: [lemmaTelemetry],
  },
});

for await (const _part of result.fullStream) {
  // stream to your response
}

​
What Lemma records

AI SDK eventLemma record
Model callGeneration with model, provider, messages, output text, and duration
Tool executionTool call with name, input, output or error, and duration
AI SDK v7 provides model and tool durations directly. AI SDK v6 provides tool execution durations; model-call durations are inferred from start and finish timestamps when the AI SDK does not provide an explicit duration. Use telemetry.functionId / experimental_telemetry.functionId for the agent name, or set it on the integration with vercelAI({ agentName: "support-agent" }). For advanced cases, you can still attach to an existing trace by passing vercelAI({ trace }) or by calling AI SDK inside a lemma.trace() callback. If you use the callback form of lemma.trace(), the callback owns trace closure. If you pass a trace handle to vercelAI({ trace }), the integration closes it automatically at the end of the AI SDK operation. Use recordInputs: false or recordOutputs: false to avoid sending prompts, tool inputs, tool outputs, or model output text. 
telemetry: {
  integrations: [
    vercelAI({
      recordInputs: false,
      recordOutputs: false,
    }),
  ],
}